Channel width optimized neural networks for liver and vessel segmentation in liver iron quantification.

INTRODUCTION: MRI T2* relaxometry protocols are often used for Liver Iron Quantification in patients with hemochromatosis. Several methods exist to semi-automatically segment parenchyma and exclude vessels for this calculation. PURPOSE: To determine if inclusion of multiple echoes inputs to Convolutional Neural Networks (CNN) improves automated liver and vessel segmentation in MRI T2* relaxometry protocols and to determine if the resultant segmentations agree with manual segmentations for liver iron quantification analysis. METHODS: Multi echo Gradient Recalled Echo (GRE) MRI sequence for T2* relaxometry was performed for 79 exams on 31 patients with hemochromatosis for iron quantification analysis. 275 axial liver slices were manually segmented as ground truth masks. A batch normalized U-Net with variable input width to incorporate multiple echoes is used for segmentation, using DICE as the accuracy metric. ANOVA is used to evaluate significance of channel width changes in segmentation accuracy. Linear regression is used to model the relationship of channel width on segmentation accuracy. Liver segmentations are applied to relaxometry data to calculate liver T2* yielding liver iron concentration(LIC) derived from literature based calibration curves. Manual and CNN based LIC values are compared with Pearson correlation. Bland altman plots are used to visualize differences between manual and CNN based LIC values. RESULTS: Performance metrics are tested on 55 hold out slices. Linear regression indicates that there is a monotonic increase of DICE with increasing channel depth (p = 0.001) with a slope of 3.61e-3. ANOVA indicates a significant increase segmentation accuracy over single channel starting at 3 channels. Incorporation of all channels results in an average DICE of 0.86, an average increase of 0.07 over single channel. The calculated LIC from CNN segmented livers agrees well with manual segmentation (R = 0.998, slope = 0.914, p«0.001), with an average absolute difference 0.27 ± 0.99 mg Fe/g or 1.34 ± 4.3%. CONCLUSION: More input echoes yields higher model accuracy until the noise floor. Echos beyond the first three echo times in GRE based T2* relaxometry do not contribute significant information for segmentation of liver for LIC calculation. Deep learning models with three channel width allow for generalization of model to protocols of more than three echoes, effectively a universal requirement for relaxometry. Deep learning segmentations achieve a good accuracy compared with manual segmentations with minimal preprocessing. Liver iron values calculated from hand segmented liver and Neural network segmented liver were not statistically different from each other.

Dosimetric benefits of gantry-static couch-motion (GsCM) technique for breast boost radiation therapy: Reduced dose to organs-at-risk and improved dosimetric indices.

To evaluate the clinical feasibility and dosimetric benefits of a novel gantry-static couch-motion (GsCM) technique for external beam photon boost treatment of lumpectomy cavity in patients with early-stage breast cancer in comparison to three-dimensional conformal radiotherapy (3D-CRT), wedge pair in supine position (WPS), and wedge pair in decubitus position (WPD) techniques. A retrospective review was conducted on breast patients (right breast, n = 10 and left breast, n = 10) who received 10 Gy boost after 50 Gy to whole breast. The treatment plans were generated using an isocentric-based GsCM technique (a VMAT type planning approach) integrating couch rotational motion at static gantry positions. Static fields for each tangential side were merged using a Matlab® script and delivered automatically within the Varian TruebeamTM STx in Developer Mode application as a VMAT arc (wide-angular medial and short-angular lateral arcs). The dosimetric accuracy of the plan delivery was evaluated by ion chamber array measurements in phantom. For both right and left breast boost GsCM, 3D-CRT, WPS, and WPD all provided an adequate coverage to PTV. GsCM significantly reduced the ipsilateral lung V30% for right side (mean, 80%) and left side (mean, 70%). Heart V5% reduced by 90% (mean) for right and 80% (mean) for left side. Ipsilateral breast V50% and mean dose were comparable for all techniques but for GsCM, V100% reduced by 50% (mean) for right and left side. The automated delivery of both arcs was under 2 min as compared to delivering individual fields (30 ± 5 min). The gamma analysis using 2 mm distance to agreement (DTA) and 2% dose difference (DD) was 98 ± 1.5% for all 20 plans. The GsCM technique facilitates coronal plane dose delivery appropriate for deep-seated breast boost cavities, with sufficient dose conformity of target volume paired with sparing of the OARs.

Fetal radiation dose during gestation estimated on an anthropomorphic phantom for three generations of CT scanners.

OBJECTIVE: The purpose of this study is to determine fetal dose during four different stages of pregnancy for both pulmonary CT angiogram and abdominal and pelvic CT examination on 4-, 16-, and 64-MDCT scanners measured in an anthropomorphic phantom simulating a pregnant patient. MATERIALS AND METHODS: Pulmonary angiograms and abdominal and pelvic studies were performed on a phantom on 4-, 16-, and 64-MDCT scanners. Fetal positioning and mean fetal depth were determined using data from ultrasound examinations of a large cohort of patients. Scans were performed for early pregnancy and for 10, 18, and 36 weeks. Gestational age, fetal dose, and entrance skin exposure were measured. RESULTS: When constant parameters were used for pulmonary CT angiograms, the fetal radiation dose was not significantly associated with gestational age. For abdominal examinations, the 64-MDCT scanner imparted a 20% higher dose during the third trimester than did the other scanners. When scanning parameters were kept constant between machines, gestational age and fetal dose were not significantly different. However, when the manufacturer-recommended protocols for pregnant patients were used, the dose was significantly higher in the third trimester on the 64-MDCT scanner. CONCLUSION: The 64-MDCT scanner is the most dose-efficient machine when the fetus is outside the direct scan volume, as in the case of pulmonary angiograms. For abdominal examinations, the 64-MDCT scanner imparted the highest fetal dose. This finding is attributable to the increased tube current used to penetrate the larger amount of soft tissue in late pregnancy. Abdominal shielding may reduce fetal dose without affecting diagnostic ability.

Dynamic infrared imaging for the detection of malignancy.

The potential for malignancy detection using dynamic infrared imaging (DIRI) has been investigated in an animal model of human malignancy. Malignancy was apparent in images formed at the vasomotor and cardiogenic frequencies of tumour bearing mice. The observation of malignancy was removed by the administration of an agent that blocks vasodilation caused by nitric oxide (NO). Image patterns similar to those that characterize malignancy could be mimicked in normal mice using an NO producing agent. Apparently DIRI allows for cancer detection in this model through vasodilation caused by malignancy generated NO. Dynamic infrared detection of vasomotor and cardiogenic surface perfusion was validated in human subjects by a comparison with laser Doppler flowmetry (LDF). Dynamic infrared imaging technology was then applied to breast cancer detection. It is shown that dynamic infrared images formed at the vasomotor and cardiogenic frequencies of the normal and malignant breast have image pattern differences, which may allow for breast cancer detection.

Detection of breast malignancy: diagnostic MR protocol for improved specificity.

PURPOSE: To prospectively determine if a combined magnetic resonance (MR) protocol that includes T1-weighted dynamic contrast agent-enhanced (DCE) MR imaging, hydrogen 1 (1H) MR spectroscopy, and T2*-weighted perfusion MR imaging improves specificity in the diagnosis of breast cancer. MATERIALS AND METHODS: The combined MR imaging-MR spectroscopy protocol was performed in 50 patients after positive findings at mammography but prior to biopsy. Single-voxel proton MR spectroscopy and perfusion MR imaging were conducted only if DCE MR images showed rapid contrast enhancement in the lesion. Biopsy results were used as the reference for comparison with MR results and for calculation of sensitivity and specificity in the detection of breast malignancy. RESULTS: DCE MR imaging alone showed 100% sensitivity and 62.5% specificity. The specificity improved to 87.5% with the addition of 1H MR spectroscopy and to 100% with the further addition of perfusion MR imaging. Twenty-eight patients underwent both MR spectroscopy and perfusion MR imaging. Two patients underwent MR spectroscopy but declined to undergo perfusion MR imaging. The remaining 20 patients had negative results at DCE MR imaging and therefore did not undergo the additional examinations. CONCLUSION: The combined MR protocol of DCE MR imaging, 1H MR spectroscopy, and perfusion MR imaging has high sensitivity and specificity in the diagnosis of breast cancer.

Response of rat intracranial 9L gliosarcoma to microbeam radiation therapy.

Radiotherapeutic doses for malignant gliomas are generally palliative because greater, supposedly curative doses would impart clinically unacceptable damage to nearby vital CNS tissues. To improve radiation treatment for human gliomas, we evaluated microbeam radiation therapy, which utilizes an array of parallel, microscopically thin (<100 microm) planar beams (microbeams) of synchrotron-generated X rays. Rats with i.c. 9L gliosarcoma tumors were exposed laterally to a single microbeam, 27 pm wide and 3.8 mm high, stepwise, to produce irradiation arrays with 50, 75, or 100 microm of on-center beam spacings and 150, 250, 300, or 500 Gy of in-slice, skin-entrance, single-exposure doses. The resulting array size was 9 mm wide and 10.4 mm high (using three 3.8-mm vertical tiers); the beam's median energy was -70 keV. When all data were collated, the median survival was 70 days; no depletion of nerve cells was observed. However, when data from the highest skin-entrance dose and/or the smallest microbeam spacings were excluded, the median survival time of the subset of rats was 170 days, and no white matter necrosis was observed. Others have reported unilateral single-exposure broad-beam irradiation of i.c. 9L gliosarcomas at 22.5 Gy with a median survival of only -34 days and with severe depletion of neurons. These results suggest that the therapeutic index of unidirectional microbeams is larger than that of the broad beams and that an application for microbeam radiation therapy in treating certain malignant brain tumors may be found in the future.